LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from information disconnection and limited receptive field, especially for the sparse distant points. In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones. We design radial window self-attention that partitions the space into multiple non-overlapping narrow and long windows. It overcomes the disconnection issue and enlarges the receptive field smoothly and dramatically, which significantly boosts the performance of sparse distant points. Moreover, to fit the narrow and long windows, we propose exponential splitting to yield fine-grained position encoding and dynamic feature selection to increase model representation ability. Notably, our method ranks 1st on both nuScenes and SemanticKITTI semantic segmentation benchmarks with 81.9% and 74.8% mIoU, respectively. Also, we achieve the 3rd place on nuScenes object detection benchmark with 72.8% NDS and 68.5% mAP. Code is available at https://github.com/dvlab-research/SphereFormer.git.

本文提出了一种名为SphereFormer的方法，通过设计射线窗口自我关注机制，将密集的近距离点聚集到稀疏的远距离点，从而扩大感受野，提高了稀疏远距离点的性能，并在nuScenes和SemanticKITTI语义分割基准测试排名第一，取得了显著的性能提升。

基于激光雷达的三维识别球形变压器